Microsoft Technology Licensing, LLC

Jeffrey G Brown

Khaled Salah Sedky

Oliver H Foehr

Jerry Jay Dunietz

Ming Gang Liu

Andrey Shur

Charles Lamanna

Jesse D McGatha

Mauktik Gandhi

Ahmet Gurcan

Eric Stanfield Leese

Rodrigo Lopez

Abhijat A Kanade

Robledo Pontes-Filho

A classification application identifies patterns and evidences within representative documents. The application constructs a classification rule according to an entity and an affinity determined from the patterns and evidences. The application processes the representative documents with the classification rule to evaluate whether the rules meet acceptance requirements. Subsequent to a successful evaluation, the application identifies confidence levels for patterns and evidences within other documents.

Determining document classification probabilistically through classification rule analysis

Various technologies and techniques detect lists in vector graphics based documents and use them in meaningful ways. The system detects at least one list in a vector graphics based document using a set of rules. Pattern detection logic identifies characters, symbols, numbers, letters, and/or images that may start a list. Additional pattern detection logic determines if a list exists. The system can identify and parse bulleted lists, numbered or lettered lists, and nested lists that are any combination of both. Once identified, the content is translated into a modified format. The content can be output to a destination application in the modified format that is more suitable for output or use by the destination application.

Detection of lists in vector graphics documents

Various technologies and techniques detect tables in vector graphics based documents and use them in meaningful ways. The system detects at least one table in a vector graphics based document using a set of rules. The rules include analyzing a set of content representing horizontal and vertical lines to find intersections and identifying table cells based on the intersections. Once identified, the table content is translated into a modified format. The content can be output to a destination application in the modified format that is more suitable for output or use by the destination application.

Analyzing lines to detect tables in documents

Growing community of inventors

Auburn, WA, United States of America

Jeffrey G Brown